Combined texture analysis and machine learning in suspicious calcifications detected by mammography: Potential to avoid unnecessary stereotactical biopsies

Abstract

To investigate whether combined texture analysis and machine learning can distinguish malignant from benign suspicious mammographic calcifications, to find an exploratory rule-out criterion to potentially avoid unnecessary benign biopsies. Methods: Magnification views of 235 patients which underwent vacuum-assisted biopsy of suspicious calcifications (BI-RADS 4) during a two-year period were retrospectively analyzed using the texture analysis tool MaZda (Version 4.6). Microcalcifications were manually segmented and analyzed by two readers, resulting in 249 image features from gray-value histogram, gray-level co-occurrence and run-length matrices. After feature reduction with principal component analysis (PCA), a multilayer perceptron (MLP) artificial neural network was trained using histological results as the reference standard. For training and testing of this model, the dataset was split into 70 % and 30 %. ROC analysis was used to calculate diagnostic performance indices. Results: 226 patients (150 benign, 76 malignant) were included in the final analysis due to missing data in 9 cases. Feature selection yielded nine image features for MLP training. Area under the ROC-curve in the testing dataset (n = 54) was 0.82 (95 %-CI: 0.70− 0.94) and 0.832 (95 %-CI 0.72− 0.94) for both readers, respectively. A high sensitivity threshold criterion was identified in the training dataset and successfully applied to the testing dataset, demonstrating the potential to avoid 37.1-45.7 % of unnecessary biopsies at the cost of one falsenegative for each reader. Conclusion:Combined texture analysis and machine learning could be used for risk stratification in suspicious mammographic calcifications. At low costs in terms of false-negatives, unnecessary biopsies could be avoided.

Can supplementary contrast-enhanced MRI of the breast avoid needle biopsies in suspicious microcalcifications seen on mammography? A systematic review and meta-analysis

“…This pretest probability could be determined by malignancy rates associated with BI-RADS features as suggested by the literature [3] which have also been combined into multivariable risk scores [37]. Recently, also machine-learning methods have been employed for risk stratification of breast calcifications [38]. The lack of validation studies and the encouraging results reported here suggest a prospective trial on the clinical use of using breast MRI as an additional test in mammographic BI-RADS 4 microcalcifications to avoid unnecessary biopsies.…”

Images Are Data: A Breast Imaging Perspective on a Contemporary Paradigm

“…2 Application of radiomics and AI to improve the diagnostic accuracy of breast imaging. Stelzer et al examined the radiomic signatures of microcalcifications in 235 patients [69]. All findings were assessed as suspicious in conventional visual analysis (BI-RADS IV) and therefore bioptically confirmed.…”

“…Therefore, radiomic signatures may be considered accurate, workflow-friendly, and cost effective which is why they provide value to patient care (modified and reprinted with permission [69]). [69]. Alle Befunde wurden in der konventionellen visuellen Analyse (BI-RADS IV) als verdächtig bewertet und daher bioptisch bestätigt.…”

“…Results are available in real time, not requiring additional imaging or invasive procedures. Therefore, radiomic signatures may be considered accurate, workflow-friendly, and cost effective which is why they provide value to patient care (modified and reprinted with permission [69]). [69].…”

Towards Accurate Diagnosis of Skin Lesions Using Feedforward Back Propagation Neural Networks

“…For years, numerous studies have been devoted to the early diagnosis of melanoma using various computational methods. Machine Learning techniques as part of Computer-Aided Diagnosis have been applied successfully for the detection of polyps in colonoscopy [ 9 , 10 ], calcifications in mammography [ 11 ], chest imaging [ 12 ], automated solutions for melanoma diagnosis using dermoscopic images [ 13 , 14 , 15 ] and non-invasive methods of recognition of the finger skin [ 16 ]. In another approach, the features extracted from the pixels of a lesion were handled by a Stack-Based Auto-Encoder, and various classification methods like Principal Component Analysis, Recurrent Neural Networks and a Softmax Linear Classifier were utilized for automatic diagnosis of pigmented skin lesions [ 17 ].…”